US 12,450,937 B2
Automatic form document processing
Aviral Sharma, Jaipur (IN); Jatin Lamba, Kheri (IN); Shreyansh Nanawati, Kalyan (IN); and Dinesh Bajaj, Gurugram (IN)
Assigned to Optum, Inc., Minnetonka, MN (US)
Filed by Optum, Inc., Minnetonka, MN (US)
Filed on Dec. 6, 2022, as Appl. No. 18/062,099.
Prior Publication US 2024/0185630 A1, Jun. 6, 2024
Int. Cl. G06V 30/416 (2022.01); G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/19 (2022.01); G06V 30/414 (2022.01)
CPC G06V 30/416 (2022.01) [G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/19173 (2022.01); G06V 30/414 (2022.01)] 15 Claims
OG exemplary drawing
 
8. A system comprising:
one or more processors; and
one or more memories storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
identifying a plurality of entities in a form document;
for each entity of the plurality of entities, generating a vector for the entity of a plurality of vectors, respectively, wherein the vector for the entity comprises a plurality of values describing content of the entity and describing a position of the entity within the form document;
identifying a plurality of pairs of the plurality of entities that satisfy a spatial relationship requirement;
determining a plurality of semantic relationships between the plurality of pairs of the plurality of entities that satisfy the spatial relationship requirement, wherein determining the plurality of semantic relationships between the plurality of pairs of the plurality of entities that satisfy the spatial relationship requirement comprises, for each pair of entities in the plurality of pairs of entities satisfying the spatial relationship requirement, applying a classification machine-learned (ML) model that takes as input a first vector and a second vector of the plurality of vectors for a first entity and a second entity of the pair of entities, respectively, and outputs a first category for the first entity of the pair of entities and a second category for the second entity of the pair of entities, wherein a combination of the first category for the first entity and the second category for the second entity represents a semantic relationship among the plurality of semantic relationships between the first entity and the second entity; and
processing the form document based on the plurality of semantic relationships between the plurality of pairs of the plurality of entities that satisfy the spatial relationship requirement.